Chang Liu

Chang Liu

Auto-generated profile, based on publicly available information

Chang Liu

Department of Computer Science, Harbin Institute of Technology, Heilongjiang 150001, China

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 October 2017 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
CLChang Liu
Chang Liu
PLPeng Liu
Peng Liu
WZWei Zhao
Wei Zhao
XTXianglong Tang
Xianglong Tang
Robust object tracking and re-detection require stably predicting the trajectory of the target object and recovering from tracking failure by quickly re-detecting it when it is lost during long-term tracking. The locations of the target and the background are calculated relative to the region occupied by the object. The effect of tracking can be enhanced by isolating the target and the background, modeling and tracking them, respectively, and integrating their tracking results. In this study, we propose an approach that builds motion models for the target and its context. Tracking results from a target tracker and a context tracker are integrated through linear fusion to predict the position of the target. A kernelized correlation filter (KCF) tracker is used to track the target in the predicted position. When the target is lost, it can be quickly recovered by searching in the given field of view using a target model built and updated through observation models that are constructed prior to the loss of the target. Our approach is not sensitive to the segmentation of the target and the context. The motion models and observation models of the target and the context work together in the tracking process, whereas the target model alone is involved in re-detection. Experiments to test our proposed approach, which simultaneously models the target and its context, showed that it can effectively enhance the robustness of long-term tracking.

1 March 2019 in Pattern Recognition
Verified
Journal Article
Closed access
PLPeng Liu
Peng Liu
CLChang Liu
Chang Liu
WZWei Zhao
Wei Zhao
XTXianglong Tang
Xianglong Tang

28 August 2019 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
CLChang Liu
Chang Liu
PLPeng Liu
Peng Liu
WZWei Zhao
Wei Zhao
XTXianglong Tang
Xianglong Tang
In this paper, we propose a novel channel pruning method for convolutional neural network (CNN)-based trackers. Pre-trained CNNs are widely used in visual tracking to obtain high-level representations of targets. However, most pre-trained CNNs are trained for other tasks (e.g., VGGNet is trained for image classification), and they require a considerable amount of time to generate features. First, we introduce a dimensionality reduction method considering the information amount and tracking errors to obtain good low-dimensionality features from the last convolutional layer for tracking. Then, a backward channel selection method is proposed to select representative channels layer by layer. In this process, we aim to minimize the target changes and maximize the loss of the background or other objects. Finally, we reconstruct the neural network weights to reduce the information loss of the target with one-shot learning. Experimental results on challenging benchmarks show that the proposed channel pruning method can enhance the tracking performance and reduce the computational requirements.

25 July 2009
Verified
Conference Paper
Closed access
PDF file
HWHua Wei
Hua Wei
DGDengteng Ge
Dengteng Ge
ZFZeng Fan
Zeng Fan
CLChang Liu
Chang Liu
XHXiaodong He
Xiaodong He
YLYao Li
Yao Li
As a kind of intelligent temperature-sensitive polymer, the poly (N-isopropylacrylamide) (PNIPA) hydrogel has lower critical solution temperature (LCST) of 33°C. PNIPA could change from transparency to opacification due to its phase separation. In this work, silicone coatings were doped with PNIPA particles, which were obtained by rotary cutting after N-isopropylacrylamide cross link reaction between N-isopropylacrylamide and N, N-methylenebisacrylamide in the aqueous solution below 20°C. The morphology and optical properties were characterized by SEM, FTIR and UV-Vis-NIR, respectively. The results show that combination of silicone resin and PNIPA particles enhances the diffuse reflection and operability in applications. It proves that the reversible thermal chronic property of PNIPA is useful for intelligent thermal control application.